Wireless communication method, terminal device, and network device

By transmitting target information between terminal devices and network devices to manage and optimize the activation of artificial intelligence models, the problem of poor model performance in the prior art is solved, system performance and spectrum efficiency are improved, and model training and data are improved. Collection efficiency.

WO2024229632A1PCT designated stage expired Publication Date: 2024-11-14GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Patent Information

Application Number
PCT/CN2023/092586
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-06
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

The prior art is difficult to effectively manage and optimize the performance of artificial intelligence or machine learning models in mobile communications, resulting in poor system performance indicators and spectrum efficiency, and low model training and data set acquisition efficiency.

Method used

By transmitting target information between terminal devices and network devices, determining the AI ​​capabilities or activation information of models corresponding to multiple functions, we can achieve better key performance indicators, system throughput and spectrum efficiency, and improve model training and data Efficiency of centralized acquisition.

Benefits of technology

It achieves higher system performance indicators and spectrum efficiency, reduces the time for model training and data set acquisition, adapts to changes in different scenarios, and ensures the performance of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023092586_14112024_PF_FP_ABST
    Figure CN2023092586_14112024_PF_FP_ABST
Patent Text Reader

Abstract

A wireless communication method, a terminal device, and a network device, which are beneficial for ensuring the performance of a model. The method comprises: a terminal device receiving target information sent by a network device, wherein the target information is used for determining activation information of artificial intelligence (AI) capabilities corresponding to a plurality of functions or activation information of models corresponding to the plurality of functions.
Need to check novelty before this filing date? Find Prior Art

Description

Wireless communication method, terminal device and network device Technical Field

[0001] The embodiments of the present application relate to the field of communications, and specifically to a wireless communication method, terminal device, and network device. Background Art

[0002] In some scenarios, it is considered to use artificial intelligence (AI) models or machine learning (ML) models to implement some functionalities or features of mobile communication processing to obtain certain performance gains.

[0003] Therefore, how to manage models based on functions or features to ensure model performance is an urgent problem that needs to be solved.

[0004] Summary of the Invention

[0005] The present application provides a wireless communication method, terminal device and network device, which are conducive to ensuring the performance of the model.

[0006] In a first aspect, a method for wireless communication is provided, including: a terminal device receives target information sent by a network device, wherein the target information is used to determine activation information of artificial intelligence (AI) capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

[0007] In a second aspect, a method for wireless communication is provided, including: a network device sends target information to a terminal device, wherein the target information is used to determine activation information of artificial intelligence (AI) capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

[0008] In a third aspect, a terminal device is provided for executing the method in the above-mentioned first aspect or its various implementations.

[0009] Specifically, the terminal device includes a functional module for executing the method in the above-mentioned first aspect or its various implementation modes.

[0010] In a fourth aspect, a network device is provided for executing the method in the above second aspect or its various implementations.

[0011] Specifically, the network device includes a functional module for executing the method in the above-mentioned second aspect or its various implementation modes.

[0012] In a fifth aspect, a terminal device is provided, comprising a processor and a memory, wherein the memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method of the first aspect or its respective implementations.

[0013] In a sixth aspect, a network device is provided, comprising a processor and a memory, wherein the memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method of the second aspect or its respective implementations.

[0014] In a seventh aspect, a chip is provided for implementing the method described in any one of the first and second aspects above, or their respective implementations. Specifically, the chip includes a processor configured to load and execute a computer program from a memory, causing a device equipped with the chip to perform the method described in any one of the first and second aspects above, or their respective implementations.

[0015] In an eighth aspect, a computer-readable storage medium is provided for storing a computer program, which enables a computer to execute the method of any one of the first to second aspects or their respective implementations.

[0016] In a ninth aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method of any one of the first to second aspects or their respective implementations.

[0017] In a tenth aspect, a computer program is provided, which, when executed on a computer, enables the computer to execute the method of any one of the first to second aspects or their respective implementations.

[0018] Through the above technical solution, network equipment can indicate the activation information of corresponding AI capabilities or models for multiple functions, that is, multiple functions can correspond to the activation information of the same AI capability or model. Compared with implementing each function through an independent model, better key performance indicators (KPI) performance, system throughput and spectrum efficiency can be obtained, and the efficiency of model training and data set acquisition can also be greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.

[0020] FIG2 is a schematic diagram showing the connections of neurons in a neural network.

[0021] FIG3 is a schematic structural diagram of a neural network.

[0022] FIG4 is a schematic diagram of a convolutional neural network.

[0023] FIG5 is a schematic structural diagram of an LSTM unit.

[0024] FIG6 is a schematic interaction diagram of a wireless communication method provided according to an embodiment of the present application.

[0025] 7 to 22 are schematic diagrams of the correspondence between functions and models according to embodiments of the present application.

[0026] Figure 23 is a schematic block diagram of a terminal device provided according to an embodiment of the present application.

[0027] Figure 24 is a schematic block diagram of a network device provided according to an embodiment of the present application.

[0028] Figure 25 is a schematic block diagram of a communication device provided according to an embodiment of the present application.

[0029] Figure 26 is a schematic block diagram of a chip provided according to an embodiment of the present application.

[0030] Figure 27 is a schematic block diagram of a communication system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. With respect to the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0032] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity) system. Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.

[0033] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0034] Optionally, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) networking scenario.

[0035] Optionally, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, where the authorized spectrum can also be considered as an unshared spectrum.

[0036] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0037] The terminal device can be a station (ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0038] In an embodiment of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0039] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0040] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0041] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.

[0042] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.

[0043] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0044] For example, a communication system 100 used in an embodiment of the present application is shown in FIG1 . The communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or a communication terminal or terminal). The network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices within the coverage area.

[0045] FIG1 exemplarily shows a network device and two terminal devices. Optionally, the communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0046] Optionally, the communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0047] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system 100 shown in FIG1 as an example, the communication device may include a network device 110 and a terminal device 120 having a communication function. The network device 110 and the terminal device 120 may be the specific devices described above and will not be described in detail here. The communication device may also include other devices in the communication system 100, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0048] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.

[0049] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0050] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0051] In the embodiments of the present application, "pre-defined" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device or a network device). The present application does not limit the specific implementation method. For example, pre-defined may refer to information defined in a protocol.

[0052] In the embodiments of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and this application does not limit this.

[0053] To facilitate a better understanding of the embodiments of the present application, the neural network and machine learning related to the present application are explained.

[0054] A neural network (NN) is a computational model consisting of multiple interconnected neuron nodes, where the connections between nodes represent weighted values ​​from input signals to output signals, called weights. Each node performs weighted summation (SUM) on different input signals and outputs them through a specific activation function (f). Figure 2 is a schematic diagram of a neuron structure, where a1, a2, …, an represent input signals, w1, w2, …, wn represent weights, f represents the activation function, and t represents the output.

[0055] A simple neural network, shown in Figure 3, consists of an input layer, hidden layers, and an output layer. By using different connections, weights, and activation functions among multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. Each node in the previous level is connected to all nodes in the next level. This neural network is a fully connected neural network, also known as a deep neural network (DNN).

[0056] The basic structure of a convolutional neural network (CNN) consists of an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer, as shown in Figure 4. Each neuron in the convolutional kernel of a convolutional layer is locally connected to its input. The introduction of a pooling layer extracts the local maximum or average features of a layer, effectively reducing network parameters and exploiting local features, enabling the CNN to converge quickly and achieve excellent performance.

[0057] Deep learning utilizes deep neural networks with multiple hidden layers, significantly improving the network's ability to learn features and fitting complex, nonlinear mappings from input to output. Consequently, it has found widespread application in speech and image processing. In addition to deep neural networks, deep learning also includes other commonly used basic structures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for different tasks.

[0058] The basic structure of a convolutional neural network includes an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer, as shown in Figure 4. Each neuron in the convolution kernel of the convolutional layer is locally connected to its input, and the introduction of the pooling layer extracts the local maximum or average features of a certain layer, effectively reducing the network parameters and mining local features, enabling the convolutional neural network to converge quickly and achieve excellent performance.

[0059] RNNs are neural networks that model sequential data and have achieved remarkable success in natural language processing applications such as machine translation and speech recognition. Specifically, network devices memorize information from past moments and use it in the calculation of current outputs. This means that nodes in hidden layers are no longer disconnected but connected, and the input to a hidden layer includes not only the input layer but also the output of the previous hidden layer. Common RNN structures include long short-term memory (LSTM) and gated recurrent unit (GRU). Figure 5 shows a basic LSTM cell structure, which can include a tanh activation function. Unlike RNNs, which only consider the most recent state, the LSTM cell state determines which states should be retained and which should be forgotten, addressing the long-term memory limitations of traditional RNNs.

[0060] In some scenarios, AI models or ML models are considered to implement some functionalities or features of the air interface, such as channel estimation and channel state information (CSI) feedback.

[0061] In some implementations, each function or feature corresponds to one or more AI / ML models, that is, each function or feature corresponds to an independent AI / ML model. However, in some scenarios, multiple functions or features are interrelated, and jointly training an AI / ML model for these multiple functions or features can achieve better system performance. For example, jointly training an AI / ML model for channel estimation and CSI feedback can achieve better system performance.

[0062] In this case, how to manage the models for the multiple functions or features (eg, activation or selection of the models) is an issue that needs to be addressed urgently.

[0063] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0064] FIG6 is a schematic diagram of a wireless communication method 200 according to an embodiment of the present application. As shown in FIG6 , the method 200 includes the following contents:

[0065] S210, the terminal device receives target information sent by the network device, where the target information is used to determine activation information of AI capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

[0066] In some embodiments, the target information used to determine activation information of AI capabilities or models corresponding to multiple functions may include:

[0067] The target information includes activation information of AI capabilities or models corresponding to multiple functions; or,

[0068] The target information includes activation information of AI capabilities or models corresponding to some of the multiple functions, and the activation information of AI capabilities or models corresponding to other functions is determined based on the activation information of the AI ​​capabilities or models corresponding to the said some functions. For example, the activation information of the AI ​​capabilities or models corresponding to other functions is the same as the activation information of the AI ​​capabilities or models corresponding to the said some functions, or there is an association between the two.

[0069] In some embodiments, activation information of AI capabilities or models corresponding to multiple functions can be used to indicate whether the AI ​​capabilities or models corresponding to the multiple functions are activated, and / or the AI ​​capabilities or models activated for the multiple functions.

[0070] For example, the activation information of the AI ​​capabilities corresponding to the multiple functions may include whether the AI ​​capabilities corresponding to the multiple functions are activated, that is, whether AI algorithms or models are used for the multiple functions.

[0071] For another example, the activation information of the models corresponding to multiple functions includes whether the models corresponding to the multiple functions are activated and / or the models activated among the models corresponding to the multiple functions. That is, whether a model is used for the multiple functions and / or which model is used when the model is used. Therefore, in the embodiments of the present application, model activation can be implemented, and when multiple models exist for the multiple functions, model selection can also be performed.

[0072] In some embodiments, the target information may be one piece of information, that is, the network device may indicate activation information of AI capabilities or models corresponding to multiple functions through one piece of information.

[0073] It should be understood that the embodiment of the present application does not limit the carrying method of the target information. For example, the target information can be carried through existing signaling, specifically, for example, carried in a reserved field or a newly added field in the existing signaling. For another example, the target information can also be carried through newly added signaling.

[0074] In some embodiments, the target information may be carried by control information, and the control information may be, for example, downlink control information (DCI).

[0075] In some embodiments, the target information may be carried via Media Access Control (MAC) signaling, such as a Media Access Control Control Element (MAC CE).

[0076] In some embodiments, the target information may also be carried by higher layer signaling, such as Radio Resource Control (RRC) signaling.

[0077] In some embodiments, the target information is carried via application layer control information.

[0078] In some embodiments, the target information is carried by DCI, and the activation information of the AI ​​capability or model corresponding to the carrying function can be indicated by the format of DCI, Radio Network Temporary Identity (RNTI) or a field in DCI.

[0079] For example, when the DCI is in the first format, it indicates that the DCI is used to carry activation information of the AI ​​capability or model corresponding to the function.

[0080] For another example, when the DCI is generated through the first RNTI, it indicates that the DCI is used to carry activation information of the AI ​​capability or model corresponding to the function.

[0081] For another example, an indication field is added to the DCI to indicate whether the DCI is used to carry activation information for the AI ​​capability or model corresponding to the function. Alternatively, when the value of an existing field in the DCI is a preset value (e.g., an invalid value), it indicates that the DCI is used to carry activation information for the AI ​​capability or model corresponding to the function.

[0082] In the embodiments of the present application, functionality may also be replaced by feature. Functionality is used as an example for explanation below, but the present application is not limited thereto.

[0083] In some embodiments, a function may be a mobile communication processing function.

[0084] For example, the functions used for mobile communication processing in the terminal device can be divided into multiple mobile communication processing functions, which can be used to process air interface data and / or high-layer data in mobile communications, where the high layer can be a MAC layer or an RRC layer.

[0085] In some embodiments, the mobile communication processing function may include but is not limited to at least one of the following functions:

[0086] Channel estimation, channel state information feedback (CSI feedback), demodulation, channel decoding, beam management, and wireless positioning.

[0087] In a specific embodiment, the channel estimation function, the CSI feedback function, the demodulation function, and the channel decoding function each correspond to a function, which are respectively recorded as function 1, function 2, function 3, and function 4.

[0088] In some embodiments, a function may be a parameter configuration combination, or in other words, a function may be described by a parameter configuration combination.

[0089] In some embodiments, the parameter configuration combination may include one parameter configuration, or a combination of multiple parameter configurations.

[0090] That is, a function can be described by one parameter configuration or multiple parameter configurations.

[0091] For example, the parameter configuration combination may be a combination of antenna port number configuration and frequency band parameter configuration.

[0092] Exemplarily, the parameter configuration combination can be sub-band level CSI feedback for 4 antenna ports (i.e., the number of antenna ports is 4, and the frequency band parameter configuration is sub-band), or full-band CSI feedback for 2 antenna ports (i.e., the number of antenna ports is 2, and the frequency band parameter configuration is full-band).

[0093] For another example, the parameter configuration combination may be a combination of a beam number configuration and a spatial domain prediction or a time domain prediction configuration of the beam.

[0094] Exemplarily, the parameter configuration combination can be spatial prediction of 16 beams (ie, the number of beams is 16, spatial prediction configuration), or time domain prediction of 8 beams (ie, the number of beams is 8, time domain prediction configuration).

[0095] In some embodiments, a function may be an application scenario, or in other words, a function may be described by an application scenario.

[0096] For example, the application scenario may be a positioning scenario, and different positioning scenarios correspond to different functions.

[0097] For example, indoor positioning, outdoor positioning, CSI feedback of indoor hotspot channels, CSI feedback of outdoor wide-coverage channels, etc. correspond to different functions respectively.

[0098] In some embodiments, the AI ​​capabilities corresponding to the multiple functions may refer to whether AI algorithms are used to implement the multiple functions.

[0099] In some embodiments, when the AI ​​capabilities corresponding to multiple functions are activated, it indicates that the AI ​​algorithm is used; otherwise, it indicates that the AI ​​algorithm is not used.

[0100] In the embodiment of the present application, AI capabilities can be replaced by ML capabilities.

[0101] In some embodiments, the models corresponding to the multiple functions may refer to models used to implement the multiple functions, wherein the correspondence between the models and the functions is described below.

[0102] It should be understood that this application does not limit the types of models corresponding to multiple functions. For example, it can be a convolutional neural network model, a recurrent neural network model, a deep learning model, etc. This application is not limited to this.

[0103] In some embodiments, the multiple functions may correspond to one AI capability or one model (or, multiple functions may correspond to the same AI capability or model). This is referred to as Method 1. In this case, the granularity of the AI ​​capability or model is multiple functions.

[0104] Here, multiple functions corresponding to one model may mean that the multiple functions can be implemented through one model, or in other words, each of the multiple functions can be implemented through the model.

[0105] Multiple functions corresponding to one AI capability may mean that the multiple functions use the same AI capability, that is, the multiple functions all activate the AI ​​capability, or all deactivate the AI ​​capability.

[0106] In other embodiments, each of the multiple functions corresponds to an AI capability or a model (or, multiple functions correspond to independent AI capabilities or models). This is referred to as approach 2. In this case, the granularity of the AI ​​capability or model is function.

[0107] Here, each function corresponds to a model, which may mean that one function can be implemented through one model, that is, each of the multiple functions corresponds to an independent model.

[0108] Each function corresponds to an AI capability, which may mean that multiple functions use independent AI capabilities, that is, the activation or deactivation of the AI ​​capabilities corresponding to different functions are independent.

[0109] In some other embodiments, the multiple functions form a function group (denoted as a first function group), and the first function group corresponds to one AI capability or one model. This is denoted as method 3. In this case, the granularity of the AI ​​capability or model is the function group.

[0110] In some embodiments, since the models in Method 1 and Method 3 need to be jointly trained based on the data sets of multiple functions, the complexity of the model implemented by Method 2 is lower than the complexity of the model implemented by Method 1 and Method 3, but the performance of the model implemented by Method 1 and Method 3 is better than the performance of the model implemented by Method 2.

[0111] In some scenarios, the terminal device only supports multiple functions corresponding to one AI capability or one model.

[0112] In this case, multiple functions correspond to one AI capability or one model.

[0113] In some scenarios, the terminal device supports both multiple functions corresponding to one AI capability or one model, and each of multiple functions corresponding to one AI capability or one model.

[0114] In this case, multiple functions can correspond to one AI capability or one model, and each of the multiple functions can also correspond to one AI capability or one model. In other words, multiple functions can be implemented by one AI capability or model, and each of the multiple functions can also be implemented by one AI capability or model.

[0115] In some scenarios, the terminal device only supports a function group consisting of multiple functions corresponding to one AI capability or one model.

[0116] In this case, a functional group consisting of multiple functions corresponds to one AI capability or one model.

[0117] In some scenarios, the terminal device supports both a function group consisting of multiple functions corresponding to one AI capability or one model, and each of the multiple functions corresponding to one AI capability or one model.

[0118] In this case, a function group consisting of multiple functions can correspond to one AI capability or one model, and each of the multiple functions can also correspond to one AI capability or one model. In other words, a function group consisting of multiple functions can be implemented by one AI capability or model, and each of the multiple functions can also be implemented by one AI capability or model.

[0119] In some embodiments, each function may be indicated by an identifier, for example, the identifier of the function may be the number of the function.

[0120] In some embodiments, the correspondence between functions and identifiers may be predefined, configured by the network device, or determined and notified by the terminal device to the network device. That is, the network device and the terminal device have the same understanding of the correspondence between functions and identifiers.

[0121] In some embodiments, each functional group may be indicated by an identifier. For example, the identifier of the functional group may be the number of the functional group.

[0122] In some embodiments, the correspondence between the functional groups and the identifiers may be predefined, configured by the network device, or determined by the terminal device. After the terminal device determines the correspondence, it may notify the network device. That is, the network device and the terminal device have the same understanding of the correspondence between the functional groups and the identifiers.

[0123] In some embodiments, the model may be indicated by an identifier, for example, the identifier of the model may be the number of the model.

[0124] In some embodiments, the correspondence between the model and the identifier may be predefined, configured by the network device, or determined and notified to the network device by the terminal device, that is, the network device and the terminal device have the same understanding of the correspondence between the model and the identifier.

[0125] In some embodiments, the network device and the terminal device have the same understanding of the models corresponding to multiple functions.

[0126] That is, the network device can know how many candidate models the multiple functions correspond to and which candidate models they correspond to.

[0127] In some embodiments, the correspondence between the multiple functions and models may be configured by the network device, or notified to the network device after the terminal device determines it, or may be predefined.

[0128] The specific implementation of target information is described below with reference to specific embodiments.

[0129] Embodiment 1: The target information includes activation information of the AI ​​capability or model jointly indicated by the multiple functions.

[0130] In this embodiment 1, the multiple functions may correspond to one AI capability or model. Therefore, the network device may jointly indicate activation information of the corresponding AI capabilities or models for the multiple functions. The joint indication here may refer to indicating activation information of the AI ​​or models corresponding to the multiple functions through one information, that is, the activation information of the AI ​​capability or model is for each of the multiple functions.

[0131] Example 1-1: Jointly indicating whether to activate (or use) AI capabilities or models for multiple functions.

[0132] In some embodiments, for the scenario in the aforementioned method 1, that is, the multiple functions correspond to one AI capability or one model (or, the multiple functions correspond to the same AI capability or model), the target information includes first indication information, and the first indication information is used to indicate whether to activate the one AI capability or one model.

[0133] In this embodiment 1-1, the number of candidate models corresponding to the multiple functions is one. When the first indication information indicates activation of the AI ​​capability, the one candidate model can be considered activated. When the first indication information indicates deactivation of the AI ​​capability, the one candidate model can be considered deactivated.

[0134] Exemplarily, the first indication information includes identification information of each of the multiple functions and a first activation indication, where the first activation indication is used to indicate whether to activate the one AI capability or model. That is, the network device can jointly indicate whether to activate the one AI capability or model for multiple functions through a first activation indication.

[0135] In some embodiments, the identification information of the function may be a number of the function.

[0136] In some embodiments, the first activation indication may be 1 bit, and different values ​​of the 1 bit are used to indicate whether the AI ​​capabilities or models corresponding to the multiple functions are activated. For example, a value of 1 indicates activation, a value of 0 indicates inactivation (or deactivation), or a value of 0 indicates activation, and a value of 1 indicates inactivation.

[0137] 7 , an example is given in which multiple functions correspond to one model, wherein function 1 and function 2 correspond to model A, and function 3 and function 4 correspond to model B.

[0138] In this example, the network device may indicate whether to activate model A for function 1 and function 2 through one indication message, and indicate whether to activate model B for function 3 and function 4 through another indication message.

[0139] Therefore, the embodiments of the present application can support the implementation of multiple functions through one model, and can activate or deactivate the models corresponding to the multiple functions through an indication message. Compared with the implementation of each function through an independent model, better key performance indicators (KPI) performance, system throughput and spectrum efficiency can be obtained, and the efficiency of model training and data set acquisition can also be greatly improved.

[0140] In other embodiments, for the scenario in which the aforementioned method 1 and method 2 are combined, that is, multiple functions correspond to the same AI capability or model, and each of the multiple functions may also correspond to an independent AI capability or model, the network device may indicate through indication information whether to activate the AI ​​capability or the corresponding model for each function, and / or whether to activate the AI ​​capability or the corresponding model for multiple functions.

[0141] For example, in the scenario shown in FIG8 , function 1 and function 2 correspond to model A (i.e., model A can implement function 1 and function 2), and function 1 also corresponds to model 1 (i.e., model 1 can implement function 1), function 2 also corresponds to model 2 (i.e., model 2 can implement function 2), function 3 and function 4 correspond to model B (i.e., model B can implement function 3 and function 4), and function 3 also corresponds to model 3 (i.e., model 3 can implement function 3), and function 4 also corresponds to model 4 (i.e., model 4 can implement function 4). In this case, the network device can indicate whether to activate model 1 for function 1 through one indication message, indicate whether to activate model 2 for function 2 through one indication message, indicate whether to activate model 3 for function 3 through one indication message, indicate whether to activate model 4 for function 4 through one indication message, and can also indicate whether to activate model A for functions 1 and 2 through one indication message, and indicate whether to activate model B for functions 3 and 4 through one indication message.

[0142] In some embodiments, the model corresponding to a single function or multiple functions is activated by default, or is deactivated by default.

[0143] Optionally, when the network device does not indicate whether to activate the corresponding model for a single function or multiple functions, the model corresponding to the single function or multiple functions is activated or deactivated by default, or the status of the model corresponding to the single function or multiple functions remains unchanged, that is, it continues to remain activated, or continues to remain deactivated.

[0144] Therefore, the embodiments of the present application can simultaneously support the implementation of multiple functions through one model and the implementation of one function through one model. In this case, the network device can activate the model corresponding to a single function through indication information, or activate the models corresponding to multiple functions, so that the terminal device can flexibly select a low-complexity model (a model corresponding to a single function) or a model with better performance (i.e., a model corresponding to multiple functions) according to the instructions of the network device.

[0145] Embodiment 1-2: A target model in which a network device jointly indicates activation of multiple functions.

[0146] The joint indication here may refer to indicating the activation of target models for multiple functions through one information, that is, the target model is for each of the multiple functions.

[0147] In some embodiments, the multiple functions correspond to several candidate models, wherein each candidate model is used to implement the multiple functions (that is, there are multiple candidate models that can implement the multiple functions), and the target information includes second indication information and / or third indication information, the second indication information is used to indicate whether to activate the AI ​​capabilities or models corresponding to the multiple functions, and the third indication information is used to indicate the activation of the target candidate model among the several candidate models.

[0148] For example, the target information may include second indication information, and the second indication information is used to indicate the deactivation of AI capabilities or models corresponding to multiple functions, that is, the multiple functions are not implemented through AI algorithms or models.

[0149] For another example, the target information may include third indication information, and the second indication information is used to indicate activation of a target candidate model among the multiple candidate models, that is, the multiple functions are implemented through the target candidate model.

[0150] For another example, the target information may include second indication information and third indication information, the second indication information is used to indicate the activation of the AI ​​capabilities or models corresponding to the multiple functions, and the third indication information is used to indicate the activation of the target candidate model among the multiple candidate models.

[0151] Exemplarily, the second indication information includes identification information of each of the multiple functions and a second activation indication, where the second activation indication is used to indicate whether to activate the AI ​​capabilities or models corresponding to the multiple functions. That is, the network device can jointly indicate whether to activate the corresponding AI capabilities or models for multiple functions through a single second activation indication.

[0152] In some embodiments, the second activation indication may be 1 bit, and different values ​​of the 1 bit are used to indicate whether the AI ​​capabilities or models corresponding to the multiple functions are activated. For example, a value of 1 indicates activation, a value of 0 indicates inactivation (or deactivation), or a value of 0 indicates activation, and a value of 1 indicates inactivation.

[0153] Exemplarily, the third indication information includes a first model indication, where the first model indication is used to indicate the target candidate model.

[0154] For example, the first model indication may be identification information of the target candidate model, such as a number.

[0155] In some embodiments, the target candidate model may be selected by the network device from among the candidate models, for example, based on current channel conditions, application scenarios, etc. Therefore, compared to using a fixed model, the network device selects a model based on the application scenario, which enables the selected model to better adapt to the current scenario and ensures model performance.

[0156] This is illustrated with reference to the specific example in FIG9 . Among them, function 1 and function 2 correspond to candidate model A-1 and candidate model A-2, and function 3 and function 4 correspond to candidate model B-1, candidate model B-2, and candidate model B-3. The network device may indicate the target candidate model to be activated for function 1 and function 2 (for example, activating candidate model A-1) through an indication message, and indicate the target candidate model to be activated for function 3 and function 4 (for example, activating candidate model B-1) through an indication message. Alternatively, the network device may also indicate that the AI ​​capability is not activated for function 1 and function 2 through an indication message, and indicate that the AI ​​capability is not activated for function 3 and function 4 through an indication message.

[0157] Therefore, the embodiments of the present application can support the implementation of multiple functions through a single model, and can activate or deactivate the models corresponding to the multiple functions through a single instruction message. Compared with implementing each function through a separate model, better KPI performance, system throughput, and spectrum efficiency can be achieved, while also significantly improving the efficiency of model training and data set acquisition. Moreover, compared with activating a fixed model, the network device selects a model from multiple models, which can better adapt to changes in scenarios and ensure model performance.

[0158] In some embodiments, for the scenario in which the aforementioned method 1 and method 2 are combined, that is, multiple functions correspond to the same AI capability or model, and each of the multiple functions may also correspond to an independent AI capability or model, the network device may indicate the model to be activated for each function through indication information, and / or the model to be activated for multiple functions.

[0159] For example, in the scenario shown in Figure 10, function 1 and function 2 correspond to candidate model A-1 and candidate model A-2, and function 1 can also correspond to candidate model 1-1 and candidate model 1-2, and function 2 can also correspond to candidate model 2-1, candidate model 2-2, and candidate model 2-3; function 3 and function 4 correspond to candidate model B-1, candidate model B-2, and candidate model B-3, and function 3 can also correspond to candidate model 3-1 and candidate model 3-2, and function 4 can also correspond to candidate model 4-1, candidate model 4-2, and candidate model 4-3.

[0160] In this case, the network device can indicate the target candidate model activated for function 1 through an indication message (for example, activation candidate model 1-1), indicate the target candidate model activated for function 2 through an indication message (for example, activation candidate model 2-1), indicate the target candidate model activated for function 3 through an indication message (for example, activation candidate model 3-1), indicate the target candidate model activated for function 4 through an indication message (for example, activation candidate model 4-1), and can also indicate the target candidate model activated for function 1 and function 2 through an indication message (for example, activation candidate model A-1), and indicate the target candidate model activated for function 3 and function 4 through an indication message (for example, activation candidate model B-1).

[0161] Therefore, the embodiment of the present application can simultaneously support the implementation of multiple functions through one model and the implementation of one function through one model. In this case, the network device can activate the target candidate model for a single function or multiple functions through indication information, so that the terminal device can flexibly select a low-complexity model (a model corresponding to a single function) or a model with better performance (i.e., a model corresponding to multiple functions) according to the instructions of the network device. Compared with activating a fixed model, selecting a model from multiple models can better adapt to changes in the scene and ensure the performance of the model.

[0162] Embodiment 2: The target information includes activation information indicating an AI capability or model for a combination of the multiple functions.

[0163] In this embodiment 2, the multiple functions form a function group (referred to as a first function group), and the first function group may correspond to the same AI capability or model. In this case, the network device may indicate activation information of the corresponding AI capability or model for the first function group.

[0164] Example 2-1: Indicating whether to activate (or use) an AI capability or model for a function group.

[0165] In some embodiments, the first functional group corresponds to an AI capability or model, and the target information includes fourth indication information, where the fourth indication information is used to indicate whether to activate the AI ​​capability or model.

[0166] In this embodiment 2-1, the number of candidate models corresponding to the first functional group is one. When the fourth indication information indicates activation of the AI ​​capability, the one candidate model may be considered activated, and when the fourth indication information indicates deactivation of the AI ​​capability, the one candidate model may be considered deactivated.

[0167] Exemplarily, the fourth indication information includes identification information of the first functional group and a third activation indication, where the third activation indication is used to indicate whether to activate an AI capability or model corresponding to the first functional group. That is, the network device may indicate whether to activate the AI ​​capability or model for the first functional group using the third activation indication.

[0168] In some embodiments, the identification information of the first functional group may be the number of the first functional group.

[0169] Optionally, the third activation indication may be 1 bit, and different values ​​of the 1 bit are used to indicate whether an AI capability or model corresponding to the first functional group is activated. For example, a value of 1 indicates activation, a value of 0 indicates inactivation, or a value of 0 indicates activation, a value of 1 indicates inactivation.

[0170] It should be understood that the network device and the terminal device have the same understanding of the functions included in the first functional group. For example, the functions included in the first functional group are configured by the network device, determined and notified to the network device by the terminal device, or predefined. Compared with Example 1, Example 2 can activate or deactivate the model for the functional group, without the need for joint indication of multiple functional modules, which is conducive to reducing signaling overhead.

[0171] 11 , the example of the first function group corresponding to one model is used for illustration. Functions 1 and 2 form function group 1, corresponding to model X, and functions 3 and 4 form function group 2, corresponding to model Y. The network device can indicate whether to activate model X for function group 1 through a piece of indication information, and whether to activate model Y for function group 2 through a piece of indication information.

[0172] Therefore, the embodiments of the present application can support the combination of multiple functions through one model, and can activate or deactivate the model corresponding to the combination of multiple functions through an indication information. Compared with the implementation of each function through an independent model, better KPI performance, system throughput and spectrum efficiency can be obtained, and the efficiency of model training and data set acquisition can also be greatly improved.

[0173] In some embodiments, for scenarios combining the aforementioned methods 1 and 2, that is, a combination of multiple functions corresponds to one AI capability or one model, and each of the multiple functions may also correspond to one AI capability or one model. The network device may indicate, through indication information, whether to activate the corresponding AI capability or model for each function, and / or whether to activate the corresponding AI capability or model for the combination of multiple functions.

[0174] For example, in the scenario shown in FIG12 , function 1 and function 2 form function group 1, corresponding to model X, function 3 and function 4 form function group 2, corresponding to model Y, and function 1 may also correspond to model 1, function 2 may also correspond to model 2, function 3 may also correspond to model 3, and function 4 may also correspond to model 4. The network device may indicate whether to activate model 1 for function 1 through one indication message, whether to activate model 2 for function 2 through one indication message, whether to activate model 3 for function 3 through one indication message, whether to activate model 4 for function 4 through one indication message, whether to activate model X for function group 1 through one indication message, and whether to activate model Y for function group 2 through one indication message.

[0175] In some embodiments, the model corresponding to a function or a function group may be activated or deactivated by default.

[0176] Optionally, when the network device does not indicate whether to activate the corresponding model for a certain function (or function group), the model corresponding to the function (or function group) is activated or deactivated by default, or the state of the model corresponding to the function (or function group) remains unchanged, that is, it continues to be activated, or continues to be deactivated.

[0177] Therefore, the embodiments of the present application can simultaneously support the combination of multiple functions implemented through one model and the implementation of one function through one model. In this case, the network device can activate the model corresponding to a single function through indication information, or activate the model corresponding to the function group, so that the terminal device can flexibly select a low-complexity model (the model corresponding to a single function) or a model with better performance (i.e., the model corresponding to the function group) according to the indication of the network device.

[0178] Example 2-2: A target model indicating activation (or use) for a functional group.

[0179] In some embodiments, the first functional group corresponds to several candidate models, wherein each candidate model is used to implement the first functional group (i.e., there are multiple candidate models that can implement the first functional group), and the target information includes fifth indication information and / or sixth indication information, the fifth indication information is used to indicate whether to activate the AI ​​capability or model corresponding to the first functional group, and the sixth indication information is used to indicate the activation of a target candidate model among the several candidate models.

[0180] For example, the target information may include fifth indication information, where the fifth indication information is used to indicate deactivation of the AI ​​capability or model corresponding to the first functional group, that is, the first functional group is not implemented through the AI ​​algorithm or model.

[0181] For another example, the target information may include sixth indication information, where the sixth indication information is used to indicate activation of a target candidate model among the multiple candidate models, that is, the first function group is implemented through the target candidate model.

[0182] For another example, the target information may include fifth indication information and sixth indication information, wherein the fifth indication information is used to indicate the activation of the AI ​​capability or model corresponding to the first functional group (i.e., the use of the AI ​​algorithm or model to implement the first functional group), and the sixth indication information is used to indicate the activation of the target candidate model among the multiple candidate models.

[0183] Exemplarily, the fifth indication information includes identification information of the first functional group and a fourth activation indication, where the fourth activation indication is used to indicate whether to activate the AI ​​capability or model corresponding to the first functional group. That is, the network device can use a fourth activation indication to jointly indicate whether to activate the AI ​​capability or model corresponding to the first functional group.

[0184] In some embodiments, the identification information of the first functional group may be the number of the first functional group.

[0185] In some embodiments, the fourth activation indication may be 1 bit, and different values ​​of the 1 bit are used to indicate whether the AI ​​capability or model corresponding to the first functional group is activated. For example, a value of 1 indicates activation, a value of 0 indicates inactivation, or a value of 0 indicates activation, a value of 1 indicates inactivation.

[0186] Exemplarily, the sixth indication information includes a second model indication, where the second model indication is used to indicate the target candidate model.

[0187] For example, the second model indication may be identification information of the target candidate model, such as a number.

[0188] In some embodiments, the target candidate model may be selected by the network device from among the candidate models, for example, based on current channel conditions, application scenarios, etc. Therefore, compared to using a fixed model, the network device selects a model based on the application scenario, which enables the selected model to adapt to the current scenario and ensure the performance of the model.

[0189] This is illustrated with reference to the specific example in FIG13 . Among them, function 1 and function 2 constitute function group 1, function group 1 corresponds to candidate model A-1 and candidate model A-2, function 3 and function 4 constitute function group 2, function group 2 corresponds to candidate model B-1, candidate model B-2 and candidate model B-3. The network device may indicate the target candidate model to be activated for function group 1 (for example, activating candidate model A-1) through an indication message, and indicate the target candidate model to be activated for function group 2 (for example, activating candidate model B-1) through an indication message. Alternatively, the network device may also indicate that the AI ​​capability or model is not activated for function group 1 through an indication message, and indicate that the AI ​​capability or model is not activated for function group 2 through an indication message.

[0190] Therefore, the embodiments of the present application can support the combination of multiple functions through a single model, and can activate or deactivate the model corresponding to the combination of multiple functions through a single instruction message. Compared with implementing each function through a separate model, better KPI performance, system throughput, and spectrum efficiency can be achieved, while also significantly improving the efficiency of model training and data set acquisition. Moreover, compared with activating a fixed model, the network device selects a model from multiple models, which can better adapt to changes in scenarios and ensure model performance.

[0191] In some scenarios, for a combination of Methods 1 and 2, that is, a combination of multiple functions corresponds to one AI capability or one model, and each of the multiple functions may also correspond to one AI capability or one model. In this case, the network device can indicate the activated model for each function through indication information, or indicate the activated model for a function group.

[0192] For example, in the scenario shown in Figure 14, function 1 and function 2 constitute function group 1, function group 1 corresponds to candidate model A-1 and candidate model A-2, function 3 and function 4 constitute function group 2, function group 2 corresponds to candidate model B-1, candidate model B-2 and candidate model B-3, and function 1 can also correspond to candidate model 1-1 and candidate model 1-2, function 2 can also correspond to candidate model 2-1, candidate model 2-2 and candidate 2-3, function 3 can also correspond to candidate model 3-1 and candidate 3-2, and function 4 can also correspond to model 4-1, candidate model 4-2 and candidate 4-3. In this case, the network device can indicate the target candidate model activated for function 1 (for example, activation candidate model 1-1) through an indication message, indicate the target candidate model activated for function 2 (for example, activation candidate model 2-2) through an indication message, indicate the target candidate model activated for function 3 (for example, activation candidate model 3-1) through an indication message, indicate the target candidate model activated for function 4 (for example, activation candidate model 4-1) through an indication message, and can also indicate the target candidate model activated for function group 1 (for example, activation candidate model A-1) through an indication message, and indicate the target candidate model activated for function group 2 (for example, activation candidate model B-1) through an indication message.

[0193] Therefore, the embodiments of the present application can simultaneously support the combination of multiple functions implemented through a single model and the implementation of a single function through a single model. In this case, the network device can activate the target candidate model for a single function or function group through instruction information, so that the terminal device can flexibly select a low-complexity model or a model with better performance according to the instruction of the network device. Compared with activating a fixed model, selecting a model from multiple models can better adapt to changes in the scenario and ensure the performance of the model.

[0194] Embodiment 3: A network device indicates activation information of AI capabilities or models corresponding to some functions among multiple functions, and jointly activates or deactivates AI capabilities or models corresponding to other functions among the multiple functions.

[0195] Compared with Example 1, in Example 3, the network device can activate or deactivate AI capabilities or models only for some functions. Accordingly, the AI ​​capabilities or models corresponding to other functions are jointly activated or deactivated. There is no need to perform joint indication for multiple functions, which is beneficial to reducing signaling overhead.

[0196] In this embodiment 3, each of the multiple functions corresponds to an AI capability or a model; or

[0197] The multiple functions correspond to one AI capability or one model; or

[0198] The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model; or;

[0199] The multiple functions form a first function group, and the first function group corresponds to an AI capability or a model; or

[0200] The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, the first function group corresponds to an AI capability or a model, and each function in the multiple functions corresponds to an AI capability or a model.

[0201] That is, the correspondence between multiple functions and AI capabilities or models can be the aforementioned method 1, method 2, method 3, a combination of method 1 and method 2, or a combination of method 2 and method 3.

[0202] The specific implementation of the above correspondence relationship refers to the relevant description of the aforementioned embodiment, and for the sake of brevity, it will not be repeated here.

[0203] In some embodiments, the models corresponding to the multiple functions may be the same, or may have an associated relationship.

[0204] For example, the association relationship between the models corresponding to different functions among the multiple functions is predefined, or configured by the network device, or determined by the terminal device and notified to the network device.

[0205] In some embodiments, the network device may send tenth indication information to the terminal device, which is used to indicate the association relationship between the models corresponding to the multiple functions activated jointly.

[0206] In some embodiments, the network device may further send ninth indication information to the terminal device to indicate the joint activation of multiple functions. For example, the ninth indication information may include identification information corresponding to the multiple functions, and the AI ​​capabilities or models corresponding to the multiple functions identified by the identification information are jointly activated or deactivated.

[0207] In some embodiments, the target information includes seventh indication information, and the seventh indication information includes activation information of AI capabilities or models corresponding to some functions of the multiple functions.

[0208] For example, the seventh indication information is used to indicate whether to activate the AI ​​capabilities or models corresponding to some of the multiple functions and / or the models activated for the some of the functions.

[0209] In some embodiments, the multiple functions include a first function and a second function, and the AI ​​capabilities or models corresponding to the first function and the second function are the same, or the models corresponding to the first function and the second function are associated.

[0210] Exemplarily, the seventh indication information includes identification information of the first function and a fifth activation indication, wherein the fifth activation indication is used to indicate whether to activate the AI ​​capability or model corresponding to the first function. This example can be applicable to a scenario where the first function corresponds to a candidate model. When the fifth activation indication is used to indicate activation of the AI ​​capability or model corresponding to the first function, the terminal device can determine that the AI ​​capability or model corresponding to the second function is also activated.

[0211] Exemplarily, the seventh indication information includes identification information of the first function and a third model indication, where the third model indication is used to indicate the AI ​​capability or model activated for the first function.

[0212] This situation may be applicable to a scenario where the first function corresponds to multiple candidate models. The network device may indicate the target candidate model activated for the first function through the seventh indication information. Furthermore, the terminal device may determine the target candidate model activated for the second function. The target candidate model corresponding to the second function may be the same as the target candidate model corresponding to the first function, or may have an associated relationship.

[0213] Exemplarily, the seventh indication information includes identification information of the first function, a fifth activation indication, and a third model indication, wherein the fifth activation indication is used to indicate whether the AI ​​capability or model corresponding to the first function is activated, and the third model indication is used to indicate the model activated for the first function.

[0214] This situation can be applicable to the scenario where the first function corresponds to multiple candidate models. The network device can activate the AI ​​capability corresponding to the first function through the fifth activation indication, and indicate the target candidate model activated for the first function through the third model indication. Furthermore, the terminal device can determine the target candidate model activated for the second function, and the target candidate model corresponding to the second function and the target candidate model corresponding to the first function can be the same, or have an associated relationship.

[0215] In some embodiments, for the scenario where method 1 and method 2 are combined or method 2 and method 3 are combined, that is, each of the multiple functions may also correspond to an independent AI capability or model. In this case, the target information may also include eighth indication information, and the eighth indication information is used to indicate whether to activate the AI ​​capability or model corresponding to each function of at least one function among the multiple functions and / or the target model activated for each function.

[0216] Example 3-1: Activating or deactivating corresponding AI capabilities or models for some of multiple functions is indicated. Accordingly, the AI ​​capabilities or models corresponding to other functions in the multiple functions are also activated or deactivated. That is, the AI ​​capabilities or models corresponding to multiple functions are jointly activated or deactivated. The AI ​​capabilities or models corresponding to the multiple functions are the same, or the models corresponding to the multiple functions are associated.

[0217] For example, when the target information indicates that the AI ​​capabilities or models corresponding to some of the multiple functions are not activated, the terminal device determines that the AI ​​capabilities or models corresponding to other functions of the multiple functions are also not activated.

[0218] For another example, when the target information indicates that the AI ​​capabilities or models corresponding to some of the multiple functions are activated, the terminal device determines that the AI ​​capabilities or models corresponding to other functions of the multiple functions are also activated.

[0219] In some embodiments, the multiple functions include a first function and a second function. When the network device indicates that the AI ​​capability or model corresponding to the first function is activated, the AI ​​capability or model corresponding to the second function is also activated; when the network device indicates that the AI ​​capability or model corresponding to the first function is not activated, the AI ​​capability or model corresponding to the second function is also not activated.

[0220] Case 1: The models corresponding to multiple functions are the same.

[0221] In some embodiments, for the scenario of method 1 above, that is, the multiple functions correspond to one AI capability or model, if the target information indicates to activate or deactivate the AI ​​capability or the first model for the first function among the multiple functions, then the AI ​​capability or the first model will be activated or deactivated for all functions other than the first function.

[0222] For example, in the example of Figure 15, function 1 and function 2 correspond to model A, and function 3 and function 4 correspond to model B. When the network device indicates to activate model A for function 1, the terminal device can determine to activate model A for function 2 as well; or, when the network device indicates to deactivate model A for function 1, the terminal device can determine to deactivate model A for function 2 as well; or, when the network device indicates to activate model B for function 3, the terminal device can determine to activate model B for function 4 as well; or, when the network device indicates to deactivate model B for function 3, the terminal device can determine to deactivate model B for function 4 as well.

[0223] In some embodiments, for the scenario in which the aforementioned method 1 and method 2 are combined, that is, the multiple functions correspond to one AI capability or model, and each of the multiple functions can also correspond to an independent AI capability or model, if the target information indicates to activate or deactivate the AI ​​capability or the first model for the first function among the multiple functions, then the AI ​​capability or the first model will be activated or deactivated for all functions other than the first function.

[0224] For example, in the example of FIG16 , function 1 and function 2 correspond to model A, function 3 and function 4 correspond to model B, and function 1 may also correspond to model 1, function 2 may also correspond to model 2, function 3 may also correspond to model 3, and function 4 may also correspond to model 4. The network device may indicate through one indication information to activate or deactivate model 1 for function 1; indicate through one indication information to activate or deactivate model 2 for function 2, indicate through one indication information to activate or deactivate model 4 for function 3; indicate through one indication information to activate or deactivate model 4 for function 4; indicate through one indication information to activate or deactivate model A for function 1, in which case the terminal device may determine to activate or deactivate model A for function 2 as well; indicate through one indication information to activate or deactivate model B for function 3, in which case the terminal device may determine to activate or deactivate model B for function 4 as well.

[0225] Optionally, the network device may also indicate to the terminal device through indication information that when the AI ​​capability or model is activated or deactivated for function 1, the AI ​​capability or model is also activated or deactivated for function 2.

[0226] Optionally, the network device may also indicate to the terminal device through indication information that when the AI ​​capability or model is activated or deactivated for function 3, the AI ​​capability or model is also activated or deactivated for function 4.

[0227] In some embodiments, for the scenario of the aforementioned method 3, that is, the multiple functions constitute a first function group, and the first function group corresponds to an AI capability or a model. If the target information indicates to activate the AI ​​capability or the first model for the first function among the multiple functions, then the AI ​​capability or the first model is activated for all functions other than the first function.

[0228] Case 2: Models corresponding to multiple functions have an association relationship

[0229] In some embodiments, for the scenario of the aforementioned method 2, that is, each of the multiple functions corresponds to an independent AI capability or model, wherein the AI ​​capabilities or models corresponding to different functions of the multiple functions are associated with each other, if the target information indicates to activate or deactivate the AI ​​capability for the second function among the multiple functions, then the AI ​​capability is activated or deactivated for all functions other than the second function; or, if the target information indicates to activate or deactivate the second model for the second function among the multiple functions, then the model associated with the second model is activated or deactivated for all functions other than the second function.

[0230] For example, in the example of Figure 17, function 1 corresponds to model 1, function 2 corresponds to model 2, function 3 corresponds to model 3, and function 4 corresponds to model 4, wherein model 1 and model 2 have an association relationship, and model 3 and model 4 have an association relationship. When the network device indicates to activate model 1 for function 1, the terminal device can determine to activate model 2 for function 2; or, when the network device indicates to deactivate model 1 for function 1, the terminal device can determine to deactivate model 2 for function 2; or, when the network device indicates to activate model 3 for function 3, the terminal device can determine to activate model 4 for function 4; or, when the network device indicates to deactivate model 3 for function 3, the terminal device can determine to deactivate model 4 for function 4.

[0231] For another example, in a scenario where mode 1 and mode 2 are combined, as shown in FIG18 , function 1 corresponds to model 1, function 2 corresponds to model 2, function 3 corresponds to model 3, and function 4 corresponds to model 4. Function 1 and function 2 may further correspond to model 5 and model 6, respectively, and model 5 and model 6 are associated with each other. Function 3 and function 4 may further correspond to model 7 and model 8, respectively, and model 7 and model 8 are associated with each other. The network device may indicate through one indication message the activation or deactivation of model 1 for function 1; indicate through one indication message the activation or deactivation of model 2 for function 2; indicate through one indication message the activation or deactivation of model 4 for function 3; indicate through one indication message the activation or deactivation of model 4 for function 4; indicate through one indication message the activation or deactivation of model 5 for function 1, in which case the terminal device may determine to activate or deactivate model 6 for function 2 as well; indicate through one indication message the activation or deactivation of model 7 for function 3, in which case the terminal device may determine to activate or deactivate model 8 for function 4 as well.

[0232] Optionally, the network device may also indicate to the terminal device through indication information that when the AI ​​capability or model is activated or deactivated for function 1, the AI ​​capability or model is also activated or deactivated for function 2.

[0233] Optionally, the network device may also indicate to the terminal device through indication information that when the AI ​​capability or model is activated or deactivated for function 3, the AI ​​capability or model is also activated or deactivated for function 4.

[0234] Embodiment 3-2: An activated or deactivated model is indicated for some functions among a plurality of functions, and accordingly, the same or associated models are activated or deactivated for other functions among the plurality of functions.

[0235] In some embodiments, the target information includes an eleventh indication information, which is used to indicate the target model activated for the first function among the multiple functions. The terminal device can determine the target model activated for the second function based on the eleventh indication information. The AI ​​capabilities or models corresponding to the first function and the second function are the same, or the models corresponding to the first function and the second function are associated. The first function corresponds to multiple candidate models.

[0236] In some embodiments, the first function and the second function may be considered as associated functions, for example, the channel estimation function and the CSI feedback function are associated functions.

[0237] Case 1: The associated features correspond to the same model.

[0238] In this case, when the network device instructs activation of the first model for the first function, the first model is also activated for the second function.

[0239] In some embodiments, for the scenario of mode 1, the network device may indicate activated target models for some of the multiple functions, and correspondingly, the other functions in the multiple functions activate the same model.

[0240] For example, in the example of Figure 19, function 1 corresponds to model 1 and model 2, function 2 corresponds to model 1 and model 2, function 3 corresponds to model 3 and model 4, and function 4 corresponds to model 3 and model 4, where function 1 and function 2 are associated functions, and function 3 and function 4 are associated functions. When the network device indicates to activate model 1 for function 1, the terminal device can determine that model 1 is also activated for function 2; or, when the network device indicates to activate model 2 for function 1, the terminal device can determine that model 2 is also activated for function 2; or, when the network device indicates to activate model 3 for function 3, the terminal device can determine that model 3 is also activated for function 4; or, when the network device indicates to activate model 4 for function 3, the terminal device can determine that model 4 is also activated for function 4.

[0241] In some embodiments, for a scenario combining method 1 and method 2, the network device may indicate an activated target model for some of the multiple functions, and / or may indicate an activated target model for each of the multiple functions.

[0242] For example, in the example of Figure 20, function 1 corresponds to model 1-1 and model 1-2, function 2 corresponds to model 2-1, model 2-2 and model 2-3, function 3 corresponds to model 3-1 and model 3-2, function 4 corresponds to model 4-1, model 4-2 and model 4-3, and function 1 and function 2 (or the combination of function 1 and function 2) can also correspond to model 5 and model 6, and function 3 and function 4 (or the combination of function 3 and function 4) can also correspond to model 7 and model 8. The network device may indicate, through one indication message, the target model (e.g., model 1-1) activated for function 1 in models 1-1 and 1-2; indicate, through one indication message, the target model (e.g., model 2-3) activated for function 2 in models 2-1, 2-2, and 2-3; indicate, through one indication message, the target model (e.g., model 3-1) activated for function 3 in models 3-1 and 3-2; indicate, through one indication message, the target model (e.g., model 4-1) activated for function 4 in models 4-1, 4-2, and 4-3; and may also indicate, through one indication message, the target model (e.g., model 5) activated for function 1 in models 5 and 6. In this case, the terminal device may determine that the same model is also activated for function 2. The network device may also indicate, through one indication message, the target model (e.g., model 7) activated for function 3 in models 7 and 8. In this case, the terminal device may determine that the same model is also activated for function 4.

[0243] Case 2: The associated functions correspond to different models, and the corresponding models have an association relationship.

[0244] In this case, when the network device instructs activation of the first model for the first function, the model associated with the first model is activated for the second function.

[0245] In some embodiments, for the scenario of mode 2, the network device may indicate activated target models for some of the multiple functions, and correspondingly, the other functions in the multiple functions activate associated models.

[0246] For example, in the example of Figure 21, function 1 corresponds to model 1-1 and model 1-2, function 2 corresponds to model 2-1 and model 2-2, wherein model 1-1 and model 2-1 have an association relationship, and model 1-2 and model 2-2 have an association relationship, function 3 corresponds to model 3-1 and model 3-2, function 4 corresponds to model 4-1 and model 4-2, wherein model 3-1 and model 4-1 have an association relationship, and model 3-2 and model 4-2 have an association relationship, then when the network device indicates to activate model 1-1 for function 1, the terminal device can determine to activate model 2-1 for function 2; or, when the network device indicates to activate model 1-2 for function 1, the terminal device can determine to activate model 2-2 for function 2; or, when the network device indicates to activate model 3-1 for function 3, the terminal device can determine to activate model 4-1 for function 4; or, when the network device indicates to activate model 3-2 for function 3, the terminal device can determine to activate model 4-2 for function 4.

[0247] For another example, in the example of Figure 22, function 1 corresponds to model 1-1 and model 1-2, function 2 corresponds to model 2-1, model 2-2 and model 2-3, function 3 corresponds to model 3-1 and model 3-2, function 4 corresponds to model 4-1, model 4-2 and model 4-3, and function 1 corresponds to model 5-1 and model 5-2, function 2 corresponds to model 6-1 and model 6-2, wherein model 5-1 and model 6-1 have an association relationship, and model 5-2 and model 6-2 have an association relationship; function 3 corresponds to model 7-1 and model 7-2, function 4 corresponds to model 8-1 and model 8-2, wherein model 7-1 and model 8-1 have an association relationship, and model 7-2 and model 8-2 have an association relationship. The network device can indicate the target model (for example, model 1-1) activated for function 1 in model 1-1 and model 1-2 through an indication message; indicate the target model (for example, model 2-1) activated for function 2 in model 2-1, model 2-2 and model 2-3 through an indication message; indicate the target model (for example, model 3-1) activated for function 3 in model 3-1 and model 3-2 through an indication message; indicate the target model (for example, model 4-1) activated for function 4 in model 4-1, model 4-2 and model 4-3 through an indication message; and can also indicate the target model activated for function 1 in model 5-1 and model 5-2 through an indication message. In this case, the terminal device can determine the associated model to be activated for function 2. For example, if the network device indicates that model 5-1 is activated for function 1, the terminal device determines that model 6-1 is activated for function 2, or, if the network device indicates that model 5-2 is activated for function 1, the terminal device can determine that model 6-2 is activated for function 2. The target model activated for function 3 in model 7-1 and model 7-2 can also be indicated by an indication information. In this case, the terminal device can determine the associated model to be activated for function 4. For example, if the network device indicates that model 7-1 is activated for function 3, the terminal device determines that model 8-1 is activated for function 4, or if the network device indicates that model 7-2 is activated for function 3, the terminal device can determine that model 8-2 is activated for function 4.

[0248] Therefore, the embodiments of the present application can support the implementation of a single function, multiple functions, or a combination of multiple functions through a model. The network device can activate the target model for a single function or part of the multiple functions or part of the function group through indication information. Furthermore, the terminal device can activate the same model for other functions, or activate the model associated with the target model, so that the terminal device can flexibly select a low-complexity model or a model with better performance. Compared with activating a fixed model, selecting a model from multiple models can better adapt to changes in the scene and ensure the performance of the model.

[0249] In summary, in the embodiments of the present application, multiple functions can be implemented using the same AI capability or model, and the network device can indicate the activation information of the AI ​​capabilities or models corresponding to multiple functions through one message. Compared with implementing each function through an independent model, better KPI performance, system throughput and spectrum efficiency can be obtained, and the efficiency of model training and data set acquisition can also be greatly improved.

[0250] Furthermore, when multiple functions or a combination of multiple functions correspond to multiple candidate models, the network device can indicate the target candidate model among the multiple candidate models. Compared with activating a fixed model, selecting a model from multiple models can better adapt to changes in the scene and ensure the performance of the model.

[0251] The above text, in combination with Figures 6 to 22, describes in detail the method embodiment of the present application. The following text, in combination with Figures 23 to 27, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0252] FIG23 shows a schematic block diagram of a terminal device 400 according to an embodiment of the present application. As shown in FIG23 , the terminal device 400 includes:

[0253] The communication unit 410 is used to receive target information sent by the network device, where the target information is used to determine activation information of artificial intelligence (AI) capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

[0254] In some embodiments, the multiple functions correspond to one AI capability or one model; or

[0255] The multiple functions correspond to one AI capability or one model, and each of the multiple functions corresponds to one AI capability or one model.

[0256] In some embodiments, the target information includes activation information of the AI ​​capabilities or models jointly indicated for the multiple functions.

[0257] In some embodiments, the multiple functions correspond to one AI capability, and the target information includes first indication information, where the first indication information is used to indicate whether to activate the one AI capability.

[0258] In some embodiments, the first indication information includes identification information of each of the multiple functions and a first activation indication, where the first activation indication is used to indicate whether to activate the one AI capability.

[0259] In some embodiments, the multiple functions correspond to several candidate models, wherein each candidate model is used to implement the multiple functions, and the target information includes second indication information and / or third indication information, the second indication information is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions, and the third indication information is used to indicate the activation of the target candidate model among the several candidate models.

[0260] In some embodiments, the second indication information includes identification information of each of the multiple functions and a second activation indication, where the second activation indication is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions.

[0261] In some embodiments, the third indication information includes a first model indication, where the first model indication is used to indicate the target candidate model.

[0262] In some embodiments, the multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

[0263] In some embodiments, the target information includes activation information of the AI ​​capability or model corresponding to the first functional group.

[0264] In some embodiments, the first functional group corresponds to an AI capability, and the target information includes fourth indication information, where the fourth indication information is used to indicate whether to activate the AI ​​capability.

[0265] In some embodiments, the fourth indication information includes identification information of the first functional group and a third activation indication, where the third activation indication is used to indicate whether to activate a corresponding AI capability for the first functional group.

[0266] In some embodiments, the first functional group corresponds to several candidate models, wherein each candidate model is used to implement the first functional group, and the target information includes fifth indication information and / or sixth indication information, the fifth indication information is used to indicate whether to activate the AI ​​capability corresponding to the first functional group, and the sixth indication information is used to indicate the activation of a target candidate model among the several candidate models.

[0267] In some embodiments, the fifth indication information includes identification information of the first functional group and a fourth activation indication, where the fourth activation indication is used to indicate whether to activate the AI ​​capability corresponding to the first functional group.

[0268] In some embodiments, the sixth indication information includes identification information of the first functional group and a second model indication, where the second model indication is used to indicate the target candidate model.

[0269] In some embodiments, each of the plurality of functions corresponds to an AI capability or a model; or

[0270] The multiple functions correspond to one AI capability or one model; or

[0271] The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model; or;

[0272] The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

[0273] In some embodiments, the terminal device further includes:

[0274] a processing unit, configured to, when the target information indicates that the AI ​​capabilities or models corresponding to some of the multiple functions are not activated, determine that the AI ​​capabilities or models corresponding to other functions among the multiple functions are also not activated; or

[0275] When the target information indicates that the AI ​​capabilities or models corresponding to some of the multiple functions are activated, it is determined that the AI ​​capabilities or models corresponding to other functions of the multiple functions are also activated.

[0276] In some embodiments, the terminal device further includes:

[0277] A processing unit, configured to determine, when the target information indicates activation of an AI capability or a first model for a first function among the multiple functions, and when the multiple functions correspond to the same AI capability or model, or when the multiple functions form a first function group and the first function group corresponds to one AI capability or one model, to activate the AI ​​capability or the first model for functions other than the first function.

[0278] In some embodiments, the plurality of functions include a second function, and the terminal device further includes:

[0279] A processing unit, configured to determine, when the target information indicates activation of an AI capability or a second model for a second function among the multiple functions, and each of the multiple functions corresponds to an AI capability or model, to activate the AI ​​capability or a model associated with the second model for functions other than the second function.

[0280] In some embodiments, there is an association relationship between the AI ​​capabilities or models corresponding to different functions among the multiple functions, and the association relationship is predefined or configured by the network device.

[0281] In some embodiments, the target information includes seventh indication information, and the seventh indication information includes activation information of AI capabilities or models corresponding to some functions of the multiple functions.

[0282] In some embodiments, the seventh indication information is used to indicate whether to activate the AI ​​capabilities or models corresponding to some of the multiple functions and / or the AI ​​capabilities or models activated for the some of the functions.

[0283] In some embodiments, the multiple functions include a first function, and the seventh indication information includes identification information of the first function and a fifth activation indication, where the fifth activation indication is used to indicate whether to activate the AI ​​capability or model corresponding to the first function; or

[0284] The seventh indication information includes identification information of the first function and a third model indication, where the third model indication is used to indicate an AI capability or model activated for the first function; or

[0285] The seventh indication information includes identification information of the first function, a fifth activation indication, and a third model indication. The fifth activation indication is used to indicate whether the AI ​​capability or model corresponding to the first function is activated, and the third model indication is used to indicate the AI ​​capability or model activated for the first function.

[0286] In some embodiments, when the terminal device supports that the multiple functions correspond to one AI capability or model and each of the multiple functions corresponds to one AI capability or model, or when the terminal device supports that the combination of the multiple functions corresponds to one AI capability or model and each of the multiple functions corresponds to one AI capability or model, the target information also includes: eighth indication information, which is used to indicate activation information of the AI ​​capability or model for at least one of the multiple functions.

[0287] In some embodiments, the eighth indication information is used to indicate whether to activate the AI ​​capability or model corresponding to each of the at least one function and / or the target model activated for each function.

[0288] In some embodiments, the target information is carried by at least one of the following signaling: downlink control information DCI, media access control element MAC CE, high-layer signaling, and application layer control information.

[0289] In some embodiments, the target information is carried by DCI, the DCI is in a first format, and / or the DCI is generated by a first radio network temporary identifier RNTI, wherein the DCI in the first format is used to carry activation information of the AI ​​capability or model corresponding to the function, and the DCI generated by the first RNTI is used to carry activation information of the AI ​​capability or model corresponding to the function.

[0290] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0291] It should be understood that the terminal device 400 according to the embodiment of the present application may correspond to the terminal device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the terminal device 400 are respectively for realizing the corresponding processes of the terminal device in the method 200 shown in Figures 6 to 22. For the sake of brevity, they will not be repeated here.

[0292] FIG24 is a schematic block diagram of a network device according to an embodiment of the present application. The network device 500 of FIG24 includes:

[0293] The communication unit 510 is used to send target information to the terminal device, where the target information is used to determine activation information of artificial intelligence (AI) capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

[0294] In some embodiments, the multiple functions correspond to one AI capability or one model; or

[0295] The multiple functions correspond to one AI capability or one model, and each of the multiple functions corresponds to one AI capability or one model.

[0296] In some embodiments, the target information includes activation information of the AI ​​capabilities or models jointly indicated for the multiple functions.

[0297] In some embodiments, the multiple functions correspond to one AI capability, and the target information includes first indication information, where the first indication information is used to indicate whether to activate the one AI capability.

[0298] In some embodiments, the first indication information includes identification information of each of the multiple functions and a first activation indication, where the first activation indication is used to indicate whether to activate the one AI capability.

[0299] In some embodiments, the multiple functions correspond to several candidate models, wherein each candidate model is used to implement the multiple functions, and the target information includes second indication information and / or third indication information, the second indication information is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions, and the third indication information is used to indicate the activation of the target candidate model among the several candidate models.

[0300] In some embodiments, the second indication information includes identification information of each of the multiple functions and a second activation indication, where the second activation indication is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions.

[0301] In some embodiments, the third indication information includes a first model indication, where the first model indication is used to indicate the target candidate model.

[0302] In some embodiments, the multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

[0303] In some embodiments, the target information includes activation information of the AI ​​capability or model corresponding to the first functional group.

[0304] In some embodiments, the first functional group corresponds to an AI capability, and the target information includes fourth indication information, where the fourth indication information is used to indicate whether to activate the AI ​​capability.

[0305] In some embodiments, the fourth indication information includes identification information of the first functional group and a third activation indication, where the third activation indication is used to indicate whether to activate a corresponding AI capability for the first functional group.

[0306] In some embodiments, the first functional group corresponds to several candidate models, wherein each candidate model is used to implement the first functional group, and the target information includes fifth indication information and / or sixth indication information, the fifth indication information is used to indicate whether to activate the AI ​​capability corresponding to the first functional group, and the sixth indication information is used to indicate the activation of a target candidate model among the several candidate models.

[0307] In some embodiments, the fifth indication information includes identification information of the first functional group and a fourth activation indication, where the fourth activation indication is used to indicate whether to activate the AI ​​capability corresponding to the first functional group.

[0308] In some embodiments, the sixth indication information includes identification information of the first functional group and a second model indication, where the second model indication is used to indicate the target candidate model.

[0309] In some embodiments, each of the plurality of functions corresponds to an AI capability or a model; or

[0310] The multiple functions correspond to one AI capability or one model; or

[0311] The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model; or;

[0312] The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

[0313] In some embodiments, the communication unit 510 is further configured to:

[0314] Ninth indication information is sent to the terminal device, where the indication information is used to indicate multiple functions to be jointly activated.

[0315] In some embodiments, the ninth indication information may include identification information corresponding to the multiple functions respectively.

[0316] In some embodiments, the communication unit 510 is further configured to:

[0317] A tenth indication message is sent to the terminal device, which is used to indicate the association relationship between the models corresponding to the multiple functions activated together.

[0318] In some embodiments, the target information includes seventh indication information, and the seventh indication information includes activation information of AI capabilities or models corresponding to some functions of the multiple functions.

[0319] In some embodiments, the seventh indication information is used to indicate whether to activate the AI ​​capabilities or models corresponding to some of the multiple functions and / or the AI ​​capabilities or models activated for the some of the functions.

[0320] In some embodiments, the multiple functions include a first function, and the seventh indication information includes identification information of the first function and a fifth activation indication, where the fifth activation indication is used to indicate whether to activate the AI ​​capability or model corresponding to the first function; or

[0321] The seventh indication information includes identification information of the first function and a third model indication, where the third model indication is used to indicate an AI capability or model activated for the first function; or

[0322] The seventh indication information includes identification information of the first function, a fifth activation indication, and a third model indication. The fifth activation indication is used to indicate whether the AI ​​capability or model corresponding to the first function is activated, and the third model indication is used to indicate the AI ​​capability or model activated for the first function.

[0323] In some embodiments, when the terminal device supports that the multiple functions correspond to one AI capability or model and each of the multiple functions corresponds to one AI capability or model, or when the terminal device supports that the combination of the multiple functions corresponds to one AI capability or model and each of the multiple functions corresponds to one AI capability or model, the target information also includes: eighth indication information, which is used to indicate activation information of the AI ​​capability or model for at least one of the multiple functions.

[0324] In some embodiments, the eighth indication information is used to indicate whether to activate the AI ​​capability or model corresponding to each of the at least one function and / or the target model activated for each function.

[0325] In some embodiments, the target information is carried by at least one of the following signaling: downlink control information DCI, media access control element MAC CE, high-layer signaling, and application layer control information.

[0326] In some embodiments, the target information is carried by DCI, the DCI is in a first format, and / or the DCI is generated by a first radio network temporary identifier RNTI, wherein the DCI in the first format is used to carry activation information of the AI ​​capability or model corresponding to the function, and the DCI generated by the first RNTI is used to carry activation information of the AI ​​capability or model corresponding to the function.

[0327] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0328] It should be understood that the network device 500 according to the embodiment of the present application may correspond to the network device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the network device 500 are respectively for realizing the corresponding processes of the network device in the method 200 shown in Figures 6 to 22. For the sake of brevity, they will not be repeated here.

[0329] Figure 25 is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application. The communication device 600 shown in Figure 25 includes a processor 610, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0330] Optionally, as shown in FIG25 , the communication device 600 may further include a memory 620. The processor 610 may call and execute a computer program from the memory 620 to implement the method in the embodiment of the present application.

[0331] The memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .

[0332] Optionally, as shown in FIG25 , the communication device 600 may further include a transceiver 630 , and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0333] The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include an antenna, and the number of antennas may be one or more.

[0334] Optionally, the communication device 600 may specifically be a network device in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the network device in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0335] Optionally, the communication device 600 may specifically be a mobile terminal / terminal device in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the mobile terminal / terminal device in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0336] Figure 26 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 700 shown in Figure 26 includes a processor 710, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0337] Optionally, as shown in FIG26 , the chip 700 may further include a memory 720 , wherein the processor 710 may call and execute a computer program from the memory 720 to implement the method in the embodiment of the present application.

[0338] The memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .

[0339] Optionally, the chip 700 may further include an input interface 730. The processor 710 may control the input interface 730 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0340] Optionally, the chip 700 may further include an output interface 740. The processor 710 may control the output interface 740 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0341] Optionally, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0342] Optionally, the chip can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0343] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0344] FIG27 is a schematic block diagram of a communication system 900 provided in an embodiment of the present application. As shown in FIG27 , the communication system 900 includes a terminal device 910 and a network device 920 .

[0345] Among them, the terminal device 910 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 920 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, they will not be repeated here.

[0346] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0347] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0348] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0349] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0350] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0351] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0352] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0353] Optionally, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0354] Optionally, the computer program product can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0355] The embodiment of the present application also provides a computer program.

[0356] Optionally, the computer program can be applied to the network device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not described here.

[0357] Optionally, the computer program can be applied to the mobile terminal / terminal device in the embodiments of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0358] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0359] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0360] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0361] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0362] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0363] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0364] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The terminal device receives target information sent by the network device, and the target information is used to determine activation information of artificial intelligence AI capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

2. The method according to claim 1, characterized in that The multiple functions correspond to one AI capability or one model; or The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model.

3. The method according to claim 1 or 2, characterized in that: The target information includes activation information of the AI ​​capabilities or models jointly indicated for the multiple functions.

4. The method according to any one of claims 1 to 3, characterized in that The multiple functions correspond to one AI capability, and the target information includes first indication information, where the first indication information is used to indicate whether to activate the one AI capability.

5. The method according to claim 4, characterized in that The first indication information includes identification information of each of the multiple functions and a first activation indication, where the first activation indication is used to indicate whether to activate the one AI capability.

6. The method according to any one of claims 1 to 3, characterized in that The multiple functions correspond to several candidate models, wherein each candidate model is used to implement the multiple functions, and the target information includes second indication information and / or third indication information, the second indication information is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions, and the third indication information is used to indicate the activation of a target candidate model among the several candidate models.

7. The method according to claim 6, characterized in that The second indication information includes identification information of each of the multiple functions and a second activation indication, where the second activation indication is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions.

8. The method according to claim 6 or 7, characterized in that: The third indication information includes a first model indication, where the first model indication is used to indicate the target candidate model.

9. The method according to claim 1, characterized in that: The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

10. The method according to claim 9, characterized in that The target information includes activation information of the AI ​​capability or model corresponding to the first functional group.

11. The method according to claim 10, characterized in that The first function group corresponds to an AI capability, and the target information includes fourth indication information, where the fourth indication information is used to indicate whether to activate the AI ​​capability.

12. The method according to claim 11, characterized in that The fourth indication information includes identification information of the first function group and a third activation indication, where the third activation indication is used to indicate whether to activate the one AI capability.

13. The method according to claim 10, characterized in that The first functional group corresponds to several candidate models, wherein each candidate model is used to implement the first functional group, and the target information includes fifth indication information and / or sixth indication information, the fifth indication information is used to indicate whether to activate the AI ​​capability corresponding to the first functional group, and the sixth indication information is used to indicate the activation of a target candidate model among the several candidate models.

14. The method according to claim 13, characterized in that The fifth indication information includes identification information of the first functional group and a fourth activation indication, where the fourth activation indication is used to indicate whether to activate the AI ​​capability corresponding to the first functional group.

15. The method according to claim 13 or 14, characterized in that The sixth indication information includes a second model indication, where the second model indication is used to indicate the target candidate model.

16. The method according to claim 1, characterized in that Each of the multiple functions corresponds to an AI capability or a model; or The multiple functions correspond to one AI capability or one model; or The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model; or; The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

17. The method according to claim 16, characterized in that The method further comprises: When the target information indicates that the AI ​​capabilities or models corresponding to some of the multiple functions are not activated, determining that the AI ​​capabilities or models corresponding to other functions of the multiple functions are also not activated; or When the target information indicates that the AI ​​capabilities or models corresponding to some of the multiple functions are activated, it is determined that the AI ​​capabilities or models corresponding to other functions of the multiple functions are also activated.

18. The method according to claim 16 or 17, characterized in that The method further comprises: If the target information indicates activation of an AI capability or a first model for a first function among the multiple functions, then when the multiple functions correspond to the same AI capability or model, or when the multiple functions form a first function group and the first function group corresponds to one AI capability or one model, it is determined to activate the AI ​​capability or the first model for other functions other than the first function.

19. The method according to any one of claims 16 to 18, characterized in that: The plurality of functions includes a second function, the method further comprising: If the target information indicates activation of an AI capability or a second model for a second function among the multiple functions, and each of the multiple functions corresponds to an AI capability or model, determine to activate the AI ​​capability or a model associated with the second model for other functions other than the second function.

20. The method according to claim 19, characterized in that There is an association relationship between the AI ​​capabilities or models corresponding to different functions among the multiple functions, and the association relationship is predefined or configured by the network device.

21. The method according to any one of claims 16 to 20, characterized in that The target information includes seventh indication information, and the seventh indication information includes activation information of AI capabilities or models corresponding to some functions of the multiple functions.

22. The method according to claim 21, characterized in that The seventh indication information is used to indicate whether to activate the AI ​​capabilities or models corresponding to some of the multiple functions and / or the AI ​​capabilities or models activated for the some of the functions.

23. The method according to claim 21 or 22, characterized in that The multiple functions include a first function, the seventh indication information includes identification information of the first function and a fifth activation indication, the fifth activation indication being used to indicate whether to activate an AI capability or model corresponding to the first function; or The seventh indication information includes identification information of the first function and a third model indication, where the third model indication is used to indicate an AI capability or model activated for the first function; or The seventh indication information includes identification information of the first function, a fifth activation indication, and a third model indication, the fifth activation indication being used to indicate whether to activate the AI ​​capability or model corresponding to the first function, and the third model indication being used to indicate the AI ​​capability or model activated for the first function.

24. The method according to any one of claims 1 to 23, characterized in that When the terminal device supports one AI capability or model corresponding to the multiple functions and one AI capability or model for each of the multiple functions, or when the terminal device supports one AI capability or model corresponding to a combination of the multiple functions and one AI capability or model for each of the multiple functions, the target information also includes: eighth indication information, used to indicate activation information of the AI ​​capability or model for at least one of the multiple functions.

25. The method according to claim 24, characterized in that The eighth indication information is used to indicate whether to activate the AI ​​capability or model corresponding to each of the at least one function and / or the target model activated for each function.

26. The method according to any one of claims 1 to 25, characterized in that The target information is carried by at least one of the following signaling: downlink control information DCI, media access control element MAC CE, high-layer signaling, and application layer control information.

27. The method according to claim 26, characterized in that The target information is carried by DCI, the DCI is in a first format, and / or the DCI is generated by a first wireless network temporary identifier RNTI, wherein the DCI in the first format is used to carry activation information of the AI ​​capability or model corresponding to the function, and the DCI generated by the first RNTI is used to carry activation information of the AI ​​capability or model corresponding to the function.

28. A wireless communication method, characterized in that: include: The network device sends target information to the terminal device, where the target information is used to determine activation information of artificial intelligence AI capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

29. The method according to claim 28, characterized in that The multiple functions correspond to one AI capability or one model; or The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model.

30. The method according to claim 28 or 29, characterized in that The target information includes activation information of the AI ​​capabilities or models jointly indicated for the multiple functions.

31. The method according to any one of claims 28 to 30, characterized in that The multiple functions correspond to one AI capability, and the target information includes first indication information, where the first indication information is used to indicate whether to activate the one AI capability.

32. The method according to claim 31, characterized in that The first indication information includes identification information of each of the multiple functions and a first activation indication, where the first activation indication is used to indicate whether to activate the one AI capability.

33. The method according to any one of claims 28 to 30, characterized in that The multiple functions correspond to several candidate models, wherein each candidate model is used to implement the multiple functions, and the target information includes second indication information and / or third indication information, the second indication information is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions, and the third indication information is used to indicate the activation of a target candidate model among the several candidate models.

34. The method according to claim 33, characterized in that The second indication information includes identification information of each of the multiple functions and a second activation indication, where the second activation indication is used to indicate whether to activate the AI ​​capabilities corresponding to the multiple functions.

35. The method according to claim 33 or 34, characterized in that The third indication information includes a first model indication, where the first model indication is used to indicate the target candidate model.

36. The method according to claim 28, characterized in that The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

37. The method according to claim 36, characterized in that The target information includes activation information of the AI ​​capability or model corresponding to the first functional group.

38. The method according to claim 37, characterized in that The first functional group corresponds to an AI capability, and the target information includes fourth indication information, where the fourth indication information is used to indicate whether to activate the AI ​​capability for the first functional group.

39. The method according to claim 38, characterized in that The fourth indication information includes identification information of the first functional group and a third activation indication, where the third activation indication is used to indicate whether to activate a corresponding AI capability for the first functional group.

40. The method according to claim 37, characterized in that The first function group corresponds to several candidate models, wherein each candidate model is used to implement the combination of the multiple functions, and the target information includes fifth indication information and / or sixth indication information, the fifth indication information is used to indicate whether to activate the AI ​​capability for the first function group, and the sixth indication information is used to indicate the activation of a target candidate model among the several candidate models.

41. The method according to claim 40, characterized in that The fifth indication information includes identification information of the first functional group and a fourth activation indication, where the fourth activation indication is used to indicate whether to activate the AI ​​capability for the first functional group.

42. The method according to claim 40 or 41, characterized in that The sixth indication information includes identification information of the first function group and a second model indication, where the second model indication is used to indicate the target candidate model.

43. The method according to claim 28, characterized in that Each of the multiple functions corresponds to an AI capability or a model; or The multiple functions correspond to one AI capability or one model; or The multiple functions correspond to one AI capability or one model and each of the multiple functions corresponds to one AI capability or one model; or; The multiple functions constitute a first function group, the first function group corresponds to an AI capability or a model, or the first function group corresponds to an AI capability or a model and each of the multiple functions corresponds to an AI capability or a model.

44. The method according to claim 43, characterized in that The method further comprises: The network device sends ninth indication information to the terminal device, where the indication information is used to indicate multiple functions to be jointly activated.

45. The method according to claim 44, characterized in that The ninth indication information may include identification information corresponding to the multiple functions respectively.

46. ​​The method according to any one of claims 43 to 45, characterized in that The method further comprises: The network device sends tenth indication information to the terminal device, which is used to indicate the association relationship between the models corresponding to the multiple functions activated jointly.

47. The method according to any one of claims 28 to 46, characterized in that The target information is carried by at least one of the following signaling: downlink control information DCI, media access control element MAC CE, high-layer signaling, and application layer control information.

48. The method according to claim 47, characterized in that The target information is carried by DCI, the DCI is in a first format, and / or the DCI is generated by a first wireless network temporary identifier RNTI, wherein the DCI in the first format is used to carry activation information of the AI ​​capability or model corresponding to the function, and the DCI generated by the first RNTI is used to carry activation information of the AI ​​capability or model corresponding to the function.

49. A terminal device, characterized in that: include: A communication unit is used to receive target information sent by a network device, where the target information is used to determine activation information of artificial intelligence (AI) capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

50. A network device, characterized in that: include: A communication unit is used to send target information to a terminal device, wherein the target information is used to determine activation information of artificial intelligence AI capabilities corresponding to multiple functions or activation information of models corresponding to multiple functions.

51. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method as claimed in any one of claims 1 to 27.

52. A network device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method as claimed in any one of claims 28 to 48.

53. A chip, characterized in that: include: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 27, or a method as claimed in any one of claims 28 to 48.

54. A computer-readable storage medium, characterized in that: Used to store a computer program, the computer program causing a computer to execute the method according to any one of claims 1 to 27, or the method according to any one of claims 28 to 48.

55. A computer program product, characterized in that The method comprises computer program instructions which cause a computer to perform the method as claimed in any one of claims 1 to 27 or the method as claimed in any one of claims 28 to 48.

56. A computer program, characterized in that The computer program causes a computer to execute the method of any one of claims 1 to 27, or the method of any one of claims 28 to 48.

Citation Information

Patent Citations

  • Application release method, application use method, AI model release method and AI model release device

    CN113849777A

  • Intelligent wireless access network

    CN114095969A

  • Communication method and device

    CN114143799A

  • AI model operation method and device, AI model loading method and device and IC chip

    CN114691566A

  • Communication method and communication device applying artificial intelligence

    CN115460100A

Cited By

  • Machine learning group switching

    US12764503B2

  • Machine learning group switching

    US20240267710A1